Quantization publisher
stephenlzc
stephenlzc publishes 7 quantizations across 2 models in our index, averaging 10.680 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
2
Quantizations
7
Models covered
2
Avg effective bpw
10.680
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | stephenlzc | vs | Theirs | Difference |
|---|---|---|---|---|---|
| dolphin-2.9-llama3-8b | Q4_K_M | 4.58 GiB | QuantFactory | 4.58 GiB | -0.0% |
| dolphin-2.9-llama3-8b | Q8_0 | 7.95 GiB | QuantFactory | 7.95 GiB | -0.0% |
| dolphin-2.9-llama3-8b | Q4_K_M | 4.58 GiB | bartowski | 4.58 GiB | -0.0% |
| dolphin-2.9-llama3-8b | Q8_0 | 7.95 GiB | bartowski | 7.95 GiB | -0.0% |
| dolphin-2.9-llama3-8b | F16 | 14.97 GiB | bartowski | 14.97 GiB | -0.0% |
A quantization label describes a target, not a recipe. Publishers make different choices about which tensors to keep at higher precision, and some apply an importance matrix while others don't — so two files both honestly labelled the same thing can differ measurably in size and in quality.
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| dolphin-2.9-llama3-8b | 4 | 4.58 GiB |
| Mistral-7B-v0.3-Chinese-Chat | 3 | 4.07 GiB |